Research map / Bandits and online learning / Multi-armed bandits
Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits
Junwen Yang, Vincent Tan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use linear structure so hardness depends on the top d arms rather than all K arms | OD-LinBAI · Fixed-budget linear bandits | hardness quantity: H_{2,\mathrm{lin}}\le H_{2} \le \frac K d H_{2,\mathrm{lin}} | Improved |
| Use ε-approximate instead of exact G-optimal designs (ablation) | OD-LinBAI · Fixed-budget linear bandits | failure probability bound: 32H_{2,\mathrm{lin}} -> 32(1+\epsilon) H_{2,\mathrm{lin}} | Hurt |
| Use near-optimal designs with smaller support (ablation) | OD-LinBAI · Fixed-budget linear bandits | failure probability bound: 32H_{2,\mathrm{lin}} -> 64 H_{2,\mathrm{lin}} | Mixed |
Closest papers by meaning
- Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits (NeurIPS 2024 · similarity 0.93)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.93)
- Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback (NeurIPS 2026 · similarity 0.93)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.93)
- Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids (ICLR 2025 · similarity 0.92)
- Fixed-Budget Differentially Private Best Arm Identification (ICLR 2024 · similarity 0.92)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
